5 files changed, 660 insertions, 0 deletions
diff --git a/kernel/entry/Makefile b/kernel/entry/Makefile
new file mode 100644
index 000000000..095c775e0
--- /dev/null
+++ b/kernel/entry/Makefile
@@ -0,0 +1,13 @@
+# SPDX-License-Identifier: GPL-2.0
+
+# Prevent the noinstr section from being pestered by sanitizer and other goodies
+# as long as these things cannot be disabled per function.
+KASAN_SANITIZE := n
+UBSAN_SANITIZE := n
+KCOV_INSTRUMENT := n
+
+CFLAGS_REMOVE_common.o	 = -fstack-protector -fstack-protector-strong
+CFLAGS_common.o		+= -fno-stack-protector
+
+obj-$(CONFIG_GENERIC_ENTRY) 		+= common.o syscall_user_dispatch.o
+obj-$(CONFIG_KVM_XFER_TO_GUEST_WORK)	+= kvm.o
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
new file mode 100644
index 000000000..be61332c6
--- /dev/null
+++ b/kernel/entry/common.c
@@ -0,0 +1,483 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/context_tracking.h>
+#include <linux/entry-common.h>
+#include <linux/resume_user_mode.h>
+#include <linux/highmem.h>
+#include <linux/jump_label.h>
+#include <linux/kmsan.h>
+#include <linux/livepatch.h>
+#include <linux/audit.h>
+#include <linux/tick.h>
+
+#include "common.h"
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/syscalls.h>
+
+/* See comment for enter_from_user_mode() in entry-common.h */
+static __always_inline void __enter_from_user_mode(struct pt_regs *regs)
+{
+	arch_enter_from_user_mode(regs);
+	lockdep_hardirqs_off(CALLER_ADDR0);
+
+	CT_WARN_ON(__ct_state() != CONTEXT_USER);
+	user_exit_irqoff();
+
+	instrumentation_begin();
+	kmsan_unpoison_entry_regs(regs);
+	trace_hardirqs_off_finish();
+	instrumentation_end();
+}
+
+void noinstr enter_from_user_mode(struct pt_regs *regs)
+{
+	__enter_from_user_mode(regs);
+}
+
+static inline void syscall_enter_audit(struct pt_regs *regs, long syscall)
+{
+	if (unlikely(audit_context())) {
+		unsigned long args[6];
+
+		syscall_get_arguments(current, regs, args);
+		audit_syscall_entry(syscall, args[0], args[1], args[2], args[3]);
+	}
+}
+
+static long syscall_trace_enter(struct pt_regs *regs, long syscall,
+				unsigned long work)
+{
+	long ret = 0;
+
+	/*
+	 * Handle Syscall User Dispatch.  This must comes first, since
+	 * the ABI here can be something that doesn't make sense for
+	 * other syscall_work features.
+	 */
+	if (work & SYSCALL_WORK_SYSCALL_USER_DISPATCH) {
+		if (syscall_user_dispatch(regs))
+			return -1L;
+	}
+
+	/* Handle ptrace */
+	if (work & (SYSCALL_WORK_SYSCALL_TRACE | SYSCALL_WORK_SYSCALL_EMU)) {
+		ret = ptrace_report_syscall_entry(regs);
+		if (ret || (work & SYSCALL_WORK_SYSCALL_EMU))
+			return -1L;
+	}
+
+	/* Do seccomp after ptrace, to catch any tracer changes. */
+	if (work & SYSCALL_WORK_SECCOMP) {
+		ret = __secure_computing(NULL);
+		if (ret == -1L)
+			return ret;
+	}
+
+	/* Either of the above might have changed the syscall number */
+	syscall = syscall_get_nr(current, regs);
+
+	if (unlikely(work & SYSCALL_WORK_SYSCALL_TRACEPOINT))
+		trace_sys_enter(regs, syscall);
+
+	syscall_enter_audit(regs, syscall);
+
+	return ret ? : syscall;
+}
+
+static __always_inline long
+__syscall_enter_from_user_work(struct pt_regs *regs, long syscall)
+{
+	unsigned long work = READ_ONCE(current_thread_info()->syscall_work);
+
+	if (work & SYSCALL_WORK_ENTER)
+		syscall = syscall_trace_enter(regs, syscall, work);
+
+	return syscall;
+}
+
+long syscall_enter_from_user_mode_work(struct pt_regs *regs, long syscall)
+{
+	return __syscall_enter_from_user_work(regs, syscall);
+}
+
+noinstr long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall)
+{
+	long ret;
+
+	__enter_from_user_mode(regs);
+
+	instrumentation_begin();
+	local_irq_enable();
+	ret = __syscall_enter_from_user_work(regs, syscall);
+	instrumentation_end();
+
+	return ret;
+}
+
+noinstr void syscall_enter_from_user_mode_prepare(struct pt_regs *regs)
+{
+	__enter_from_user_mode(regs);
+	instrumentation_begin();
+	local_irq_enable();
+	instrumentation_end();
+}
+
+/* See comment for exit_to_user_mode() in entry-common.h */
+static __always_inline void __exit_to_user_mode(void)
+{
+	instrumentation_begin();
+	trace_hardirqs_on_prepare();
+	lockdep_hardirqs_on_prepare();
+	instrumentation_end();
+
+	user_enter_irqoff();
+	arch_exit_to_user_mode();
+	lockdep_hardirqs_on(CALLER_ADDR0);
+}
+
+void noinstr exit_to_user_mode(void)
+{
+	__exit_to_user_mode();
+}
+
+/* Workaround to allow gradual conversion of architecture code */
+void __weak arch_do_signal_or_restart(struct pt_regs *regs) { }
+
+static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
+					    unsigned long ti_work)
+{
+	/*
+	 * Before returning to user space ensure that all pending work
+	 * items have been completed.
+	 */
+	while (ti_work & EXIT_TO_USER_MODE_WORK) {
+
+		local_irq_enable_exit_to_user(ti_work);
+
+		if (ti_work & _TIF_NEED_RESCHED)
+			schedule();
+
+		if (ti_work & _TIF_UPROBE)
+			uprobe_notify_resume(regs);
+
+		if (ti_work & _TIF_PATCH_PENDING)
+			klp_update_patch_state(current);
+
+		if (ti_work & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL))
+			arch_do_signal_or_restart(regs);
+
+		if (ti_work & _TIF_NOTIFY_RESUME)
+			resume_user_mode_work(regs);
+
+		/* Architecture specific TIF work */
+		arch_exit_to_user_mode_work(regs, ti_work);
+
+		/*
+		 * Disable interrupts and reevaluate the work flags as they
+		 * might have changed while interrupts and preemption was
+		 * enabled above.
+		 */
+		local_irq_disable_exit_to_user();
+
+		/* Check if any of the above work has queued a deferred wakeup */
+		tick_nohz_user_enter_prepare();
+
+		ti_work = read_thread_flags();
+	}
+
+	/* Return the latest work state for arch_exit_to_user_mode() */
+	return ti_work;
+}
+
+static void exit_to_user_mode_prepare(struct pt_regs *regs)
+{
+	unsigned long ti_work;
+
+	lockdep_assert_irqs_disabled();
+
+	/* Flush pending rcuog wakeup before the last need_resched() check */
+	tick_nohz_user_enter_prepare();
+
+	ti_work = read_thread_flags();
+	if (unlikely(ti_work & EXIT_TO_USER_MODE_WORK))
+		ti_work = exit_to_user_mode_loop(regs, ti_work);
+
+	arch_exit_to_user_mode_prepare(regs, ti_work);
+
+	/* Ensure that the address limit is intact and no locks are held */
+	addr_limit_user_check();
+	kmap_assert_nomap();
+	lockdep_assert_irqs_disabled();
+	lockdep_sys_exit();
+}
+
+/*
+ * If SYSCALL_EMU is set, then the only reason to report is when
+ * SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP).  This syscall
+ * instruction has been already reported in syscall_enter_from_user_mode().
+ */
+static inline bool report_single_step(unsigned long work)
+{
+	if (work & SYSCALL_WORK_SYSCALL_EMU)
+		return false;
+
+	return work & SYSCALL_WORK_SYSCALL_EXIT_TRAP;
+}
+
+static void syscall_exit_work(struct pt_regs *regs, unsigned long work)
+{
+	bool step;
+
+	/*
+	 * If the syscall was rolled back due to syscall user dispatching,
+	 * then the tracers below are not invoked for the same reason as
+	 * the entry side was not invoked in syscall_trace_enter(): The ABI
+	 * of these syscalls is unknown.
+	 */
+	if (work & SYSCALL_WORK_SYSCALL_USER_DISPATCH) {
+		if (unlikely(current->syscall_dispatch.on_dispatch)) {
+			current->syscall_dispatch.on_dispatch = false;
+			return;
+		}
+	}
+
+	audit_syscall_exit(regs);
+
+	if (work & SYSCALL_WORK_SYSCALL_TRACEPOINT)
+		trace_sys_exit(regs, syscall_get_return_value(current, regs));
+
+	step = report_single_step(work);
+	if (step || work & SYSCALL_WORK_SYSCALL_TRACE)
+		ptrace_report_syscall_exit(regs, step);
+}
+
+/*
+ * Syscall specific exit to user mode preparation. Runs with interrupts
+ * enabled.
+ */
+static void syscall_exit_to_user_mode_prepare(struct pt_regs *regs)
+{
+	unsigned long work = READ_ONCE(current_thread_info()->syscall_work);
+	unsigned long nr = syscall_get_nr(current, regs);
+
+	CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
+
+	if (IS_ENABLED(CONFIG_PROVE_LOCKING)) {
+		if (WARN(irqs_disabled(), "syscall %lu left IRQs disabled", nr))
+			local_irq_enable();
+	}
+
+	rseq_syscall(regs);
+
+	/*
+	 * Do one-time syscall specific work. If these work items are
+	 * enabled, we want to run them exactly once per syscall exit with
+	 * interrupts enabled.
+	 */
+	if (unlikely(work & SYSCALL_WORK_EXIT))
+		syscall_exit_work(regs, work);
+}
+
+static __always_inline void __syscall_exit_to_user_mode_work(struct pt_regs *regs)
+{
+	syscall_exit_to_user_mode_prepare(regs);
+	local_irq_disable_exit_to_user();
+	exit_to_user_mode_prepare(regs);
+}
+
+void syscall_exit_to_user_mode_work(struct pt_regs *regs)
+{
+	__syscall_exit_to_user_mode_work(regs);
+}
+
+__visible noinstr void syscall_exit_to_user_mode(struct pt_regs *regs)
+{
+	instrumentation_begin();
+	__syscall_exit_to_user_mode_work(regs);
+	instrumentation_end();
+	__exit_to_user_mode();
+}
+
+noinstr void irqentry_enter_from_user_mode(struct pt_regs *regs)
+{
+	__enter_from_user_mode(regs);
+}
+
+noinstr void irqentry_exit_to_user_mode(struct pt_regs *regs)
+{
+	instrumentation_begin();
+	exit_to_user_mode_prepare(regs);
+	instrumentation_end();
+	__exit_to_user_mode();
+}
+
+noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
+{
+	irqentry_state_t ret = {
+		.exit_rcu = false,
+	};
+
+	if (user_mode(regs)) {
+		irqentry_enter_from_user_mode(regs);
+		return ret;
+	}
+
+	/*
+	 * If this entry hit the idle task invoke ct_irq_enter() whether
+	 * RCU is watching or not.
+	 *
+	 * Interrupts can nest when the first interrupt invokes softirq
+	 * processing on return which enables interrupts.
+	 *
+	 * Scheduler ticks in the idle task can mark quiescent state and
+	 * terminate a grace period, if and only if the timer interrupt is
+	 * not nested into another interrupt.
+	 *
+	 * Checking for rcu_is_watching() here would prevent the nesting
+	 * interrupt to invoke ct_irq_enter(). If that nested interrupt is
+	 * the tick then rcu_flavor_sched_clock_irq() would wrongfully
+	 * assume that it is the first interrupt and eventually claim
+	 * quiescent state and end grace periods prematurely.
+	 *
+	 * Unconditionally invoke ct_irq_enter() so RCU state stays
+	 * consistent.
+	 *
+	 * TINY_RCU does not support EQS, so let the compiler eliminate
+	 * this part when enabled.
+	 */
+	if (!IS_ENABLED(CONFIG_TINY_RCU) && is_idle_task(current)) {
+		/*
+		 * If RCU is not watching then the same careful
+		 * sequence vs. lockdep and tracing is required
+		 * as in irqentry_enter_from_user_mode().
+		 */
+		lockdep_hardirqs_off(CALLER_ADDR0);
+		ct_irq_enter();
+		instrumentation_begin();
+		kmsan_unpoison_entry_regs(regs);
+		trace_hardirqs_off_finish();
+		instrumentation_end();
+
+		ret.exit_rcu = true;
+		return ret;
+	}
+
+	/*
+	 * If RCU is watching then RCU only wants to check whether it needs
+	 * to restart the tick in NOHZ mode. rcu_irq_enter_check_tick()
+	 * already contains a warning when RCU is not watching, so no point
+	 * in having another one here.
+	 */
+	lockdep_hardirqs_off(CALLER_ADDR0);
+	instrumentation_begin();
+	kmsan_unpoison_entry_regs(regs);
+	rcu_irq_enter_check_tick();
+	trace_hardirqs_off_finish();
+	instrumentation_end();
+
+	return ret;
+}
+
+void raw_irqentry_exit_cond_resched(void)
+{
+	if (!preempt_count()) {
+		/* Sanity check RCU and thread stack */
+		rcu_irq_exit_check_preempt();
+		if (IS_ENABLED(CONFIG_DEBUG_ENTRY))
+			WARN_ON_ONCE(!on_thread_stack());
+		if (need_resched())
+			preempt_schedule_irq();
+	}
+}
+#ifdef CONFIG_PREEMPT_DYNAMIC
+#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
+DEFINE_STATIC_CALL(irqentry_exit_cond_resched, raw_irqentry_exit_cond_resched);
+#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
+DEFINE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched);
+void dynamic_irqentry_exit_cond_resched(void)
+{
+	if (!static_branch_unlikely(&sk_dynamic_irqentry_exit_cond_resched))
+		return;
+	raw_irqentry_exit_cond_resched();
+}
+#endif
+#endif
+
+noinstr void irqentry_exit(struct pt_regs *regs, irqentry_state_t state)
+{
+	lockdep_assert_irqs_disabled();
+
+	/* Check whether this returns to user mode */
+	if (user_mode(regs)) {
+		irqentry_exit_to_user_mode(regs);
+	} else if (!regs_irqs_disabled(regs)) {
+		/*
+		 * If RCU was not watching on entry this needs to be done
+		 * carefully and needs the same ordering of lockdep/tracing
+		 * and RCU as the return to user mode path.
+		 */
+		if (state.exit_rcu) {
+			instrumentation_begin();
+			/* Tell the tracer that IRET will enable interrupts */
+			trace_hardirqs_on_prepare();
+			lockdep_hardirqs_on_prepare();
+			instrumentation_end();
+			ct_irq_exit();
+			lockdep_hardirqs_on(CALLER_ADDR0);
+			return;
+		}
+
+		instrumentation_begin();
+		if (IS_ENABLED(CONFIG_PREEMPTION))
+			irqentry_exit_cond_resched();
+
+		/* Covers both tracing and lockdep */
+		trace_hardirqs_on();
+		instrumentation_end();
+	} else {
+		/*
+		 * IRQ flags state is correct already. Just tell RCU if it
+		 * was not watching on entry.
+		 */
+		if (state.exit_rcu)
+			ct_irq_exit();
+	}
+}
+
+irqentry_state_t noinstr irqentry_nmi_enter(struct pt_regs *regs)
+{
+	irqentry_state_t irq_state;
+
+	irq_state.lockdep = lockdep_hardirqs_enabled();
+
+	__nmi_enter();
+	lockdep_hardirqs_off(CALLER_ADDR0);
+	lockdep_hardirq_enter();
+	ct_nmi_enter();
+
+	instrumentation_begin();
+	kmsan_unpoison_entry_regs(regs);
+	trace_hardirqs_off_finish();
+	ftrace_nmi_enter();
+	instrumentation_end();
+
+	return irq_state;
+}
+
+void noinstr irqentry_nmi_exit(struct pt_regs *regs, irqentry_state_t irq_state)
+{
+	instrumentation_begin();
+	ftrace_nmi_exit();
+	if (irq_state.lockdep) {
+		trace_hardirqs_on_prepare();
+		lockdep_hardirqs_on_prepare();
+	}
+	instrumentation_end();
+
+	ct_nmi_exit();
+	lockdep_hardirq_exit();
+	if (irq_state.lockdep)
+		lockdep_hardirqs_on(CALLER_ADDR0);
+	__nmi_exit();
+}
diff --git a/kernel/entry/common.h b/kernel/entry/common.h
new file mode 100644
index 000000000..f6e6d02f0
--- /dev/null
+++ b/kernel/entry/common.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _COMMON_H
+#define _COMMON_H
+
+bool syscall_user_dispatch(struct pt_regs *regs);
+
+#endif
diff --git a/kernel/entry/kvm.c b/kernel/entry/kvm.c
new file mode 100644
index 000000000..2e0f75bcb
--- /dev/null
+++ b/kernel/entry/kvm.c
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/entry-kvm.h>
+#include <linux/kvm_host.h>
+
+static int xfer_to_guest_mode_work(struct kvm_vcpu *vcpu, unsigned long ti_work)
+{
+	do {
+		int ret;
+
+		if (ti_work & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) {
+			kvm_handle_signal_exit(vcpu);
+			return -EINTR;
+		}
+
+		if (ti_work & _TIF_NEED_RESCHED)
+			schedule();
+
+		if (ti_work & _TIF_NOTIFY_RESUME)
+			resume_user_mode_work(NULL);
+
+		ret = arch_xfer_to_guest_mode_handle_work(vcpu, ti_work);
+		if (ret)
+			return ret;
+
+		ti_work = read_thread_flags();
+	} while (ti_work & XFER_TO_GUEST_MODE_WORK || need_resched());
+	return 0;
+}
+
+int xfer_to_guest_mode_handle_work(struct kvm_vcpu *vcpu)
+{
+	unsigned long ti_work;
+
+	/*
+	 * This is invoked from the outer guest loop with interrupts and
+	 * preemption enabled.
+	 *
+	 * KVM invokes xfer_to_guest_mode_work_pending() with interrupts
+	 * disabled in the inner loop before going into guest mode. No need
+	 * to disable interrupts here.
+	 */
+	ti_work = read_thread_flags();
+	if (!(ti_work & XFER_TO_GUEST_MODE_WORK))
+		return 0;
+
+	return xfer_to_guest_mode_work(vcpu, ti_work);
+}
+EXPORT_SYMBOL_GPL(xfer_to_guest_mode_handle_work);
diff --git a/kernel/entry/syscall_user_dispatch.c b/kernel/entry/syscall_user_dispatch.c
new file mode 100644
index 000000000..0b6379adf
--- /dev/null
+++ b/kernel/entry/syscall_user_dispatch.c
@@ -0,0 +1,108 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020 Collabora Ltd.
+ */
+#include <linux/sched.h>
+#include <linux/prctl.h>
+#include <linux/syscall_user_dispatch.h>
+#include <linux/uaccess.h>
+#include <linux/signal.h>
+#include <linux/elf.h>
+
+#include <linux/sched/signal.h>
+#include <linux/sched/task_stack.h>
+
+#include <asm/syscall.h>
+
+#include "common.h"
+
+static void trigger_sigsys(struct pt_regs *regs)
+{
+	struct kernel_siginfo info;
+
+	clear_siginfo(&info);
+	info.si_signo = SIGSYS;
+	info.si_code = SYS_USER_DISPATCH;
+	info.si_call_addr = (void __user *)KSTK_EIP(current);
+	info.si_errno = 0;
+	info.si_arch = syscall_get_arch(current);
+	info.si_syscall = syscall_get_nr(current, regs);
+
+	force_sig_info(&info);
+}
+
+bool syscall_user_dispatch(struct pt_regs *regs)
+{
+	struct syscall_user_dispatch *sd = &current->syscall_dispatch;
+	char state;
+
+	if (likely(instruction_pointer(regs) - sd->offset < sd->len))
+		return false;
+
+	if (unlikely(arch_syscall_is_vdso_sigreturn(regs)))
+		return false;
+
+	if (likely(sd->selector)) {
+		/*
+		 * access_ok() is performed once, at prctl time, when
+		 * the selector is loaded by userspace.
+		 */
+		if (unlikely(__get_user(state, sd->selector))) {
+			force_exit_sig(SIGSEGV);
+			return true;
+		}
+
+		if (likely(state == SYSCALL_DISPATCH_FILTER_ALLOW))
+			return false;
+
+		if (state != SYSCALL_DISPATCH_FILTER_BLOCK) {
+			force_exit_sig(SIGSYS);
+			return true;
+		}
+	}
+
+	sd->on_dispatch = true;
+	syscall_rollback(current, regs);
+	trigger_sigsys(regs);
+
+	return true;
+}
+
+int set_syscall_user_dispatch(unsigned long mode, unsigned long offset,
+			      unsigned long len, char __user *selector)
+{
+	switch (mode) {
+	case PR_SYS_DISPATCH_OFF:
+		if (offset || len || selector)
+			return -EINVAL;
+		break;
+	case PR_SYS_DISPATCH_ON:
+		/*
+		 * Validate the direct dispatcher region just for basic
+		 * sanity against overflow and a 0-sized dispatcher
+		 * region.  If the user is able to submit a syscall from
+		 * an address, that address is obviously valid.
+		 */
+		if (offset && offset + len <= offset)
+			return -EINVAL;
+
+		if (selector && !access_ok(selector, sizeof(*selector)))
+			return -EFAULT;
+
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	current->syscall_dispatch.selector = selector;
+	current->syscall_dispatch.offset = offset;
+	current->syscall_dispatch.len = len;
+	current->syscall_dispatch.on_dispatch = false;
+
+	if (mode == PR_SYS_DISPATCH_ON)
+		set_syscall_work(SYSCALL_USER_DISPATCH);
+	else
+		clear_syscall_work(SYSCALL_USER_DISPATCH);
+
+	return 0;
+}